UbuntuWorld 1.0 LTS - A Platform for Automated Problem Solving & Troubleshooting in the Ubuntu OS
作者： Kartik Talamadupula , Subbarao Kambhampati , Tathagata Chakraborti , Kshitij P. Fadnis , Murray Campbell
DOI:
关键词:
摘要: In this paper, we present UbuntuWorld 1.0 LTS - a platform for developing automated technical support agents in the Ubuntu operating system. Specifically, propose to use Bash terminal as simulator of environment learning-based agent and demonstrate usefulness adopting reinforcement learning (RL) techniques basic problem solving troubleshooting environment. We provide plug-and-play interface python package where different types can be plugged evaluated, pathways integrating data from online forums like AskUbuntu into an agent's process. Finally, show that significantly improves efficiency. believe adopted real-world test bed research on support.
arxiv.org参考文章(3)
Damien Ernst, Arthur Louette, Introduction to Reinforcement Learning MIT Press. ,(1998)
Yishay Mansour, Satinder P. Singh, Richard S Sutton, David A. McAllester, Policy Gradient Methods for Reinforcement Learning with Function Approximation neural information processing systems. ,vol. 12, pp. 1057- 1063 ,(1999)
Gabriel Dulac-Arnold, Peter Sunehag, Ben Coppin, Richard Evans, Reinforcement Learning in Large Discrete Action Spaces. arXiv: Artificial Intelligence. ,(2015)